{"id":"https://openalex.org/W2147934395","doi":"https://doi.org/10.1109/icassp.2014.6854199","title":"Computationally-efficient endpointing features for natural spoken interaction with personal-assistant systems","display_name":"Computationally-efficient endpointing features for natural spoken interaction with personal-assistant systems","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2147934395","doi":"https://doi.org/10.1109/icassp.2014.6854199","mag":"2147934395"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080360704","display_name":"Harish Arsikere","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Arsikere","raw_affiliation_strings":["Electrical Engineering Department, University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080908821","display_name":"Umut \u00d6zertem","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umut Ozertem","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.61032708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3241","last_page":"3245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7862105369567871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7841473817825317},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7015321850776672},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6947997808456421},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.572845995426178},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4599643349647522},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.44455158710479736},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.41007620096206665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862105369567871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7841473817825317},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7015321850776672},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6947997808456421},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.572845995426178},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4599643349647522},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.44455158710479736},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.41007620096206665},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W68208136","https://openalex.org/W293546496","https://openalex.org/W1903951673","https://openalex.org/W1932883564","https://openalex.org/W1973120253","https://openalex.org/W1996543588","https://openalex.org/W2040256188","https://openalex.org/W2085662862","https://openalex.org/W2098929417","https://openalex.org/W2100115174","https://openalex.org/W2127305722","https://openalex.org/W2153635508","https://openalex.org/W2161274063","https://openalex.org/W2168524283","https://openalex.org/W2394998899","https://openalex.org/W2395201778","https://openalex.org/W2396703939","https://openalex.org/W2398521182","https://openalex.org/W2401232039","https://openalex.org/W2403021840","https://openalex.org/W2404117364","https://openalex.org/W2408673089","https://openalex.org/W4212783130"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2348837382","https://openalex.org/W2580934630","https://openalex.org/W2038117447"],"abstract_inverted_index":{"Current":[0],"speech-input":[1],"systems":[2],"typically":[3],"use":[4],"a":[5,39,42,56,63,114],"nonspeech":[6],"threshold":[7,59],"for":[8,14,67],"end-of-utterance":[9],"detection.":[10],"While":[11],"usually":[12],"sufficient":[13],"short":[15],"utterances,":[16],"the":[17,72,126],"approach":[18],"can":[19],"cut":[20],"speakers":[21],"off":[22],"during":[23],"pauses":[24],"in":[25,62],"more":[26],"complex":[27],"utterances.":[28],"We":[29],"elicit":[30],"personal-assistant":[31],"speech":[32,98,102],"(reminders,":[33],"calendar":[34],"entries,":[35],"messaging,":[36],"search)":[37],"using":[38,100],"recognizer":[40],"with":[41,55,125],"dramatically":[43],"increased":[44],"endpoint":[45],"threshold,":[46],"and":[47,94,122,136],"find":[48],"frequent":[49],"nonfinal":[50,82],"pauses.":[51,85],"A":[52],"standard":[53],"endpointer":[54],"500":[57],"ms":[58,116],"(latency)":[60],"results":[61,130],"36%":[64],"cutoff":[65],"rate":[66],"this":[68],"corpus.":[69],"Based":[70],"on":[71,131],"new":[73],"data,":[74],"we":[75],"develop":[76],"low-cost":[77],"acoustic":[78],"features":[79],"to":[80],"discriminate":[81],"from":[83],"final":[84],"Features":[86],"capture":[87],"periodicity,":[88],"speaking":[89],"rate,":[90],"spectral":[91],"constancy,":[92],"duration/intensity,":[93],"pitch":[95],"of":[96],"prepausal":[97],"-":[99],"no":[101],"recognition,":[103],"speaker":[104,137],"or":[105],"session":[106],"information.":[107],"Classification":[108],"experiments":[109],"yield":[110],"20%":[111],"EER":[112],"at":[113],"100":[115],"latency,":[117],"thereby":[118],"reducing":[119],"both":[120],"cutoffs":[121],"latency":[123],"compared":[124],"threshold-only":[127],"baseline.":[128],"Additional":[129],"computational":[132],"cost,":[133],"feature":[134],"importance,":[135],"differences":[138],"are":[139],"discussed.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}